agent-skill-builder

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: No evidence of malicious overrides, safety filter bypasses, or adversarial prompts. The instructions focus on legitimate architectural guidelines.- [COMMAND_EXECUTION]: The skill uses local bash commands like 'mkdir' to create the necessary directory structure for new skills in the user's home folder. This is a documented functional requirement and targets standard local paths.- [DATA_EXFILTRATION]: No network-bound commands or references to external, non-trusted domains were identified. The skill does not access sensitive credentials or personal files.- [REMOTE_CODE_EXECUTION]: The skill does not download or execute remote scripts. It provides documentation on using native tools and setting up MCP servers.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 06:57 AM